How to Use the Kisi MCP in CrewAI

Q: How do I connect the Kisi MCP Server to my CrewAI setup?

Pass the Vinkius URL directly into the mcps array in your Agent definition. For granular control, import MCPServerHTTP from crewai.mcp and instantiate it with your endpoint token.

Deploy autonomous multi-agent teams in CrewAI to monitor Kisi access logs, audit permissions, and manage physical security.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kisi MCP to CrewAI

Create your Vinkius account to connect Kisi to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kisi with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Kisi access audits to specialized CrewAI agents

Stop treating physical security as a single script. With CrewAI, you assign specific Kisi MCP Server tools to dedicated agents. You build a Security Auditor agent armed with `list_users` and `list_role_assignments`. Its only job is to find anomalies in your access matrix. While the auditor works, a Facilities Manager agent watches `list_places` and `list_locks`. If the auditor finds an unauthorized user, it passes the context to the manager agent. They share memory, so the manager knows exactly which door to lock down without you writing manual handoff code.

Build autonomous physical incident response

When an alarm triggers, speed matters. A CrewAI moderator agent takes immediate action using `unlock_door` to open emergency exits, while a separate communication agent drafts an alert. The agents coordinate the physical response autonomously. To prevent blind actions, the moderator first runs `get_lock_details` to check the current state of the hardware. It verifies the door isn't already jammed open before issuing the command. You get a coordinated, intelligent response to physical security events.

Restrict physical actions with tool filters

You rarely want an analytical agent to have the power to open doors. CrewAI lets you use `tool_filter` on the `MCPServerHTTP` connection. You expose `list_access_groups` and `get_place_details` to your reporting agent, keeping it strictly read-only. Your action agent gets a separate MCP connection that includes `unlock_door`. This enforces the principle of least privilege at the agent level. If the reporting agent hallucinates a command to open the front door, the system physically rejects it because the tool simply does not exist in its context.

Setup guide

Set up Kisi MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kisi tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kisi Analyst",
    goal="Access and analyze Kisi data via MCP.",
    backstory="Expert analyst with direct Kisi access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kisi transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kisi Analyst",
        goal="Access and analyze Kisi data via MCP.",
        backstory="Expert analyst with direct Kisi access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kisi transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kisi. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kisi now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kisi MCP in CrewAI

Pass the Vinkius URL directly into the `mcps` array in your Agent definition. For granular control, import `MCPServerHTTP` from `crewai.mcp` and instantiate it with your endpoint token.

Yes. You define the MCP connection once and assign it to multiple agents in your crew. However, using `tool_filter` to give each agent only the specific Kisi tools they need is a safer architectural pattern.

Never give analytical agents access to the unlock tool. Use `tool_filter` when attaching the server to restrict them to safe queries like `list_locks` or `list_places`. Only grant action tools to a dedicated, heavily prompted moderator agent.

Yes. If your organization has thousands of employees, the agent uses `list_users` and autonomously navigates the paginated results. It stores the relevant user IDs in its short-term memory to use in subsequent role assignment queries.

You hand an AI direct control over physical entryways and expose sensitive organizational charts via `list_access_groups`. Vinkius mitigates the infrastructure risk by running the MCP connection in a strict, ephemeral sandbox. The connection authenticates via a single endpoint token, meaning your root Kisi API keys are never exposed to the Python environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript